Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.7
2.3
Journals
Algorithms
Special Issues
Dynamic System Modelling from Data: Emerging Algorithms and Applications
share announcement

Dynamic System Modelling from Data: Emerging Algorithms and Applications

A special issue of Algorithms (ISSN 1999-4893). This special issue belongs to the section "Algorithms for Multidisciplinary Applications".

Deadline for manuscript submissions: 15 July 2024 | Viewed by 4724

Special Issue Editors

Prof. Dr. Quanmin Zhu

E-Mail Website
Guest Editor
School of Engineering, University of the West of England, Frenchay Campus, Coldharbour Lane, Bristol BS16 1QY, UK
Interests: complex dynamic system identification and control
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Jing Chen

E-Mail Website
Guest Editor
School of Science, Jiangnan University, Wu Xi 214126, China,
Interests: processing control; system identification
Dr. Ya Gu

E-Mail Website
Guest Editor
College of Information, Mechanical and Electrical Engineering, Shanghai Normal University, Shanghai 201418, China
Interests: system identification; system modeling; artificial intelligence; deep learning; machine learning.

Special Issue Information

Dear Colleagues,

Identification techniques for modelling from data, rather than from physical and chemical principles, usually include data processing, model structure detection, model parameter estimation, and post-validation. With fast-changing technology and ever-increasing computing capacity, many emerging algorithms in the fields of machine learning, big data, soft-sensor techniques, and reinforcement learning can realistically find applications in the identification of modern systems, ranging from manmade (engineering) to natural domains. On the other hand, no matter whatever algorithm is considered, some inherent issues must be overcome in one way or another, such as the proper handling of data uncertainty due to imperfect measurements that result in the presence of noise, time-delays, and data losses. Hence, a current challenge is to develop identification algorithms that will yield compact mathematical models which are useful for providing simple solutions to complex problems within a rigorous analytical framework.

The aim of this Special Issue is to report emerging novel identification algorithms for system modelling from data. The Editors welcome submissions in form of regular technical reports, comprehensive surveys, and case studies.

Specific topics of interest include but are not limited to:

  • Novel identification algorithms for systems with time-delays.
  • Recent developments of machine learning algorithms and neural networks.
  • Modelling, analysis, and intelligent control of dynamic systems.
  • Algorithms with enhanced knowledge for intelligent automation.
  • Large-scale system: structure detection/construction and parameter estimation.
  • Networked control system identification.
  • Neural-fuzzy, and other inductive algorithms in theory and/or applications.

Prof. Dr. Quanmin Zhu
Prof. Dr. Jing Chen
Dr. Ya Gu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Algorithms is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • dynamic system modelling
  • data-driven identification
  • intelligent algorithms
  • applications

Published Papers (3 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

17 pages, 10090 KiB  
Article
Pedestrian Detection Based on Feature Enhancement in Complex Scenes
by Jiao Su, Yi An, Jialin Wu and Kai Zhang
Algorithms 2024, 17(1), 39; https://doi.org/10.3390/a17010039 - 18 Jan 2024
Viewed by 1192
Abstract
Pedestrian detection has always been a difficult and hot spot in computer vision research. At the same time, pedestrian detection technology plays an important role in many applications, such as intelligent transportation and security monitoring. In complex scenes, pedestrian detection often faces some [...] Read more.
Pedestrian detection has always been a difficult and hot spot in computer vision research. At the same time, pedestrian detection technology plays an important role in many applications, such as intelligent transportation and security monitoring. In complex scenes, pedestrian detection often faces some challenges, such as low detection accuracy and misdetection due to small target sizes and scale variations. To solve these problems, this paper proposes a pedestrian detection network PT-YOLO based on the YOLOv5. The pedestrian detection network PT-YOLO consists of the YOLOv5 network, the squeeze-and-excitation module (SE), the weighted bi-directional feature pyramid module (BiFPN), the coordinate convolution (coordconv) module and the wise intersection over union loss function (WIoU). The SE module in the backbone allows it to focus on the important features of pedestrians and improves accuracy. The weighted BiFPN module enhances the fusion of multi-scale pedestrian features and information transfer, which can improve fusion efficiency. The prediction head design uses the WIoU loss function to reduce the regression error. The coordconv module allows the network to better perceive the location information in the feature map. The experimental results show that the pedestrian detection network PT-YOLO is more accurate compared with other target detection methods in pedestrian detection and can effectively accomplish the task of pedestrian detection in complex scenes. Full article
(This article belongs to the Special Issue Dynamic System Modelling from Data: Emerging Algorithms and Applications)
►▼ Show Figures

Graphical abstract

21 pages, 4480 KiB  
Article
Neural Network-Enhanced Fault Diagnosis of Robot Joints
by Yifan Zhang and Quanmin Zhu
Algorithms 2023, 16(10), 489; https://doi.org/10.3390/a16100489 - 20 Oct 2023
Cited by 1 | Viewed by 1263
Abstract
Industrial robots play an indispensable role in flexible production lines, and the faults caused by degradation of equipment, motors, mechanical system joints, and even task diversity affect the efficiency of production lines and product quality. Aiming to achieve high-precision multiple size of fault [...] Read more.
Industrial robots play an indispensable role in flexible production lines, and the faults caused by degradation of equipment, motors, mechanical system joints, and even task diversity affect the efficiency of production lines and product quality. Aiming to achieve high-precision multiple size of fault diagnosis of robotic arms, this study presents a back propagation (BP) multiclassification neural network-based method for robotic arm fault diagnosis by taking feature fusion of position, attitude and acceleration of UR10 robotic arm end-effector to establish the database for neural network training. The new algorithm achieves an accuracy above 95% for fault diagnosis of each joint, and a diagnostic accuracy of up to 0.1 degree. It should be noted that the fault diagnosis algorithm can detect faults effectively in time, while avoiding complex mathematical operations. Full article
(This article belongs to the Special Issue Dynamic System Modelling from Data: Emerging Algorithms and Applications)
►▼ Show Figures

Figure 1

32 pages, 1458 KiB  
Article
Design of PIDDα Controller for Robust Performance of Process Plants
by Muhammad Amir Fawwaz, Kishore Bingi, Rosdiazli Ibrahim, P. Arun Mozhi Devan and B. Rajanarayan Prusty
Algorithms 2023, 16(9), 437; https://doi.org/10.3390/a16090437 - 11 Sep 2023
Cited by 3 | Viewed by 1256
Abstract
Managing industrial processes in real-time is challenging due to the nonlinearity and sensitivity of these processes. This unpredictability can cause delays in the regulation of these processes. The PID controller family is commonly used in these situations, but their performance is inadequate in [...] Read more.
Managing industrial processes in real-time is challenging due to the nonlinearity and sensitivity of these processes. This unpredictability can cause delays in the regulation of these processes. The PID controller family is commonly used in these situations, but their performance is inadequate in systems and surroundings with varying set-points, longer dead times, external noises, and disturbances. Therefore, this research has developed a novel controller structure for PIDDα that incorporates the second derivative term from PIDD2 while exclusively using fractional order parameters for the second derivative term. The controllers’ robust performance has been evaluated on four simulation plants: first order, second order with time delay, third-order magnetic levitation systems, and fourth-order automatic voltage regulation systems. The controllers’ performance has also been evaluated on experimental models of pressure and flow processes. The proposed controller exhibits the least overshoot among all the systems tested. The overshoot for the first-order systems is 9.63%, for the third-order magnetic levitation system, it is 12.82%, and for the fourth-order automatic voltage regulation system, it is only 0.19%. In the pressure process plant, the overshoot is only 4.83%. All controllers for the second-order systems have a time delay, while the flow process plant has no overshoot. The proposed controller demonstrates superior settling times in various systems. For first-order systems, the settling time is 14.26 s, while in the pressure process plant, the settling time is 8.9543 s. Similarly, the proposed controllers for the second-order system with a time delay and the flow process plant have the same settling time of 46.0495 s. In addition, the proposed controller results in the lowest rise time for three different systems. The rise time is only 0.0075 s for the third-order magnetic levitation system, while the fourth-order automatic voltage regulation system has a rise time of 0.0232 s. Finally, for the flow process plant, the proposed controller has the least rise time of 25.7819 s. Thus, in all the cases, the proposed controller results in a more robust controller structure that provides the desired performance of a regular PIDD2 controller, offering better dynamic responses, shorter settling times, faster rise times, and reduced overshoot. Based on the analysis, it is evident that PIDDα outperforms both PID and FOPID control techniques due to its ability to produce a more robust control signal. Full article
(This article belongs to the Special Issue Dynamic System Modelling from Data: Emerging Algorithms and Applications)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-3
Back to TopTop